model (nn.Module) – The reference to PyTorch model instance.
attribute(inputs, baselines=None, target=None, additional_forward_args=None, return_convergence_delta=False, custom_attribution_func=None)¶
Extends DeepLift algorithm and approximates SHAP values using Deeplift. For each input sample it computes DeepLift attribution with respect to each baseline and averages resulting attributions. More details about the algorithm can be found here:
- Note that the explanation model:
Assumes that input features are independent of one another
Is linear, meaning that the explanations are modeled through the additive composition of feature effects.
Although, it assumes a linear model for each explanation, the overall model across multiple explanations can be complex and non-linear.
inputs (tensor or tuple of tensors) – Input for which attributions are computed. If forward_func takes a single tensor as input, a single input tensor should be provided. If forward_func takes multiple tensors as input, a tuple of the input tensors should be provided. It is assumed that for all given input tensors, dimension 0 corresponds to the number of examples (aka batch size), and if multiple input tensors are provided, the examples must be aligned appropriately.
baselines (scalar, tensor, tuple of scalars or tensors, callable, optional) –
Baselines define reference samples that are compared with the inputs. In order to assign attribution scores DeepLift computes the differences between the inputs/outputs and corresponding references. Baselines can be provided as:
- a single tensor, if inputs is a single tensor, with
exactly the same dimensions as inputs or the first dimension is one and the remaining dimensions match with inputs.
- a tuple of tensors, the baseline corresponding
to each tensor in the inputs’ tuple is either a tensor with matching dimensions to corresponding tensor in the inputs’ tuple or the first dimension is one and the remaining dimensions match with the corresponding input tensor.
- callable function, optionally takes inputs as an
argument and either returns a single tensor or a tuple of those.
The number of samples in the baselines’ tensors must be larger than one.
In the cases when baselines is not provided, we internally use zero scalar corresponding to each input tensor.
Output indices for which gradients are computed (for classification cases, this is usually the target class). If the network returns a scalar value per example, no target index is necessary. For general 2D outputs, targets can be either:
- a single integer or a tensor containing a single
integer, which is applied to all input examples
- a list of integers or a 1D tensor, with length matching
the number of examples in inputs (dim 0). Each integer is applied as the target for the corresponding example.
For outputs with > 2 dimensions, targets can be either:
- A single tuple, which contains #output_dims - 1
elements. This target index is applied to all examples.
- A list of tuples with length equal to the number of
examples in inputs (dim 0), and each tuple containing #output_dims - 1 elements. Each tuple is applied as the target for the corresponding example.
additional_forward_args (any, optional) – If the forward function requires additional arguments other than the inputs for which attributions should not be computed, this argument can be provided. It must be either a single additional argument of a Tensor or arbitrary (non-tuple) type or a tuple containing multiple additional arguments including tensors or any arbitrary python types. These arguments are provided to forward_func in order, following the arguments in inputs. Note that attributions are not computed with respect to these arguments. Default: None
return_convergence_delta (bool, optional) – Indicates whether to return convergence delta or not. If return_convergence_delta is set to True convergence delta will be returned in a tuple following attributions. Default: False
custom_attribution_func (callable, optional) –
A custom function for computing final attribution scores. This function can take at least one and at most three arguments with the following signature:
custom_attribution_func(multipliers, inputs, baselines)
In case this function is not provided we use the default logic defined as: multipliers * (inputs - baselines) It is assumed that all input arguments, multipliers, inputs and baselines are provided in tuples of same length. custom_attribution_func returns a tuple of attribution tensors that have the same length as the inputs. Default: None
- attributions (tensor or tuple of tensors):
Attribution score computed based on DeepLift rescale rule with respect to each input feature. Attributions will always be the same size as the provided inputs, with each value providing the attribution of the corresponding input index. If a single tensor is provided as inputs, a single tensor is returned. If a tuple is provided for inputs, a tuple of corresponding sized tensors is returned.
- delta (tensor, returned if return_convergence_delta=True):
This is computed using the property that the total sum of forward_func(inputs) - forward_func(baselines) must be very close to the total sum of attributions computed based on approximated SHAP values using Deeplift’s rescale rule. Delta is calculated for each example input and baseline pair, meaning that the number of elements in returned delta tensor is equal to the number of examples in input * number of examples in baseline. The deltas are ordered in the first place by input example, followed by the baseline. Note that the logic described for deltas is guaranteed when the default logic for attribution computations is used, meaning that the custom_attribution_func=None, otherwise it is not guaranteed and depends on the specifics of the custom_attribution_func.
- Return type
attributions or 2-element tuple of attributions, delta
>>> # ImageClassifier takes a single input tensor of images Nx3x32x32, >>> # and returns an Nx10 tensor of class probabilities. >>> net = ImageClassifier() >>> dl = DeepLiftShap(net) >>> input = torch.randn(2, 3, 32, 32, requires_grad=True) >>> # Computes shap values using deeplift for class 3. >>> attribution = dl.attribute(input, target=3)